11 citations · 12 across the 10 of their papers we have counts for
8 papers · 1 filter
Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models
Lisa Weijler, Irene Ballester, Guofeng Mei +2
Geometric foundation models, such as the Visual Geometry Grounded Transformer (VGGT), provide strong 3D priors from unposed images. However, such models operate purely in a feed-fo…
Exploring Modality Guidance to Enhance VFM-based Feature Fusion for UDA in 3D Semantic Segmentation
Johannes Spoecklberger, Wei Lin, Pedro Hermosilla +3
Vision Foundation Models (VFMs) have become a de facto choice for many downstream vision tasks, like image classification, image segmentation, and object localization. However, the…
Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene Understanding
Pedro Hermosilla, Christian Stippel, Leon Sick
Self-supervised learning has transformed 2D computer vision by enabling models trained on large, unannotated datasets to provide versatile off-the-shelf features that perform simil…
Efficient Continuous Group Convolutions for Local SE(3) Equivariance in 3D Point Clouds
Lisa Weijler, Pedro Hermosilla
Extending the translation equivariance property of convolutional neural networks to larger symmetry groups has been shown to reduce sample complexity and enable more discriminative…
On the importance of local and global feature learning for automated measurable residual disease detection in flow cytometry data
Lisa Weijler, Michael Reiter, Pedro Hermosilla +2
This paper evaluates various deep learning methods for measurable residual disease (MRD) detection in flow cytometry (FCM) data, addressing questions regarding the benefits of mode…
TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models
Lisa Weijler, Muhammad Jehanzeb Mirza, Leon Sick +2
Test-Time Training (TTT) proposes to adapt a pre-trained network to changing data distributions on-the-fly. In this work, we propose the first TTT method for 3D semantic segmentati…
PPSURF: Combining Patches and Point Convolutions for Detailed Surface Reconstruction
Philipp Erler, Lizeth Fuentes, Pedro Hermosilla +3
3D surface reconstruction from point clouds is a key step in areas such as content creation, archaeology, digital cultural heritage, and engineering. Current approaches either try…
Point Neighborhood Embeddings
Pedro Hermosilla
Point convolution operations rely on different embedding mechanisms to encode the neighborhood information of each point in order to detect patterns in 3D space. However, as convol…